Vision transformers for action recognition: A survey
Vision transformers are emerging as a powerful tool to solve computer vision problems.
Recent techniques have also proven the efficacy of transformers beyond the image domain …
Recent techniques have also proven the efficacy of transformers beyond the image domain …
Imagebind: One embedding space to bind them all
We present ImageBind, an approach to learn a joint embedding across six different
modalities-images, text, audio, depth, thermal, and IMU data. We show that all combinations …
modalities-images, text, audio, depth, thermal, and IMU data. We show that all combinations …
Multimodal learning with transformers: A survey
Transformer is a promising neural network learner, and has achieved great success in
various machine learning tasks. Thanks to the recent prevalence of multimodal applications …
various machine learning tasks. Thanks to the recent prevalence of multimodal applications …
Beyond supervised learning for pervasive healthcare
The integration of machine/deep learning and sensing technologies is transforming
healthcare and medical practice. However, inherent limitations in healthcare data, namely …
healthcare and medical practice. However, inherent limitations in healthcare data, namely …
Learning video representations from large language models
We introduce LAVILA, a new approach to learning video-language representations by
leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be …
leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be …
St-adapter: Parameter-efficient image-to-video transfer learning
Capitalizing on large pre-trained models for various downstream tasks of interest have
recently emerged with promising performance. Due to the ever-growing model size, the …
recently emerged with promising performance. Due to the ever-growing model size, the …
Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning
We present modality gap, an intriguing geometric phenomenon of the representation space
of multi-modal models. Specifically, we show that different data modalities (eg images and …
of multi-modal models. Specifically, we show that different data modalities (eg images and …
Frozen clip models are efficient video learners
Video recognition has been dominated by the end-to-end learning paradigm–first initializing
a video recognition model with weights of a pretrained image model and then conducting …
a video recognition model with weights of a pretrained image model and then conducting …
Multimae: Multi-modal multi-task masked autoencoders
We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders
(MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can …
(MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can …
All in one: Exploring unified video-language pre-training
Abstract Mainstream Video-Language Pre-training models consist of three parts, a video
encoder, a text encoder, and a video-text fusion Transformer. They pursue better …
encoder, a text encoder, and a video-text fusion Transformer. They pursue better …